## OUTEST= Output Data Set

The OUTEST= data set contains estimates of the regression coefficients.
If you use the COVOUT option in the PROC LOGISTIC statement,
the OUTEST= data set also contains
the estimated covariance matrix of the parameter estimates.
*Number of Variables and Number of Observations*

The data set contains one variable for each intercept parameter
and one variable
for each explanatory variable in the MODEL statement.
The OUTEST= data set
contains one observation for each BY group containing
the maximum likelihood estimates of the regression coefficients.
If you also use the COVOUT option in the PROC LOGISTIC statement,
there are additional observations containing the rows
of the estimated covariance matrix of the parameter estimators.
If you use the FORWARD, BACKWARD, or STEPWISE selection method, only the
estimates of the parameters and covariance matrix for the final model
are output to the OUTEST= data set.

*Variables in the Data Set*

The OUTEST= data set contains the following variables:
- any BY variables specified
- _LINK_, a character variable of length 8 with
three possible values:
CLOGLOG for the complementary log-log function, LOGIT for the
logit function, or NORMIT for the normit function
- _TYPE_, a character variable of length 8 with
two possible values:
PARMS for parameter estimates or COV for covariance estimates
- _NAME_, a character variable containing the name
of the response variable when _TYPE_=PARMS or the name of a
model parameter when _TYPE_=COV
- _STATUS_, a character variable which
indicates whether the estimates have converged
- one variable for each intercept parameter. In the
case that one BY group fits a binary response model and
another BY group fits an ordinal response model with more
than two response levels, the data set contains the
intercept variables Intercept (for the only intercept
of the binary response model) and Intercept1, ...,
Intercept
*r*, where *r* is the largest number (greater
than 1) of intercept parameters among the BY groups.
Any of these variables not pertinent to a specific BY group
have their values set to missing.
- one variable for each model parameter
and the OFFSET= variable if specified.
If an explanatory variable is not included in the final
model in a model building process, the corresponding estimates of
parameters and covariances are set to missing values.
- _LNLIKE_, the log likelihood

Copyright © 1999 by SAS Institute Inc., Cary, NC, USA. All rights reserved.